CN108182624A - Method of Commodity Recommendation, server and computer readable storage medium - Google Patents
Method of Commodity Recommendation, server and computer readable storage medium Download PDFInfo
- Publication number
- CN108182624A CN108182624A CN201711442801.3A CN201711442801A CN108182624A CN 108182624 A CN108182624 A CN 108182624A CN 201711442801 A CN201711442801 A CN 201711442801A CN 108182624 A CN108182624 A CN 108182624A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- shopping
- identity information
- favorable rating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of Method of Commodity Recommendation, this method includes：When detecting default shopping website or shopping APP is opened, the identity information for the user for currently browsing the shopping website or the APP that does shopping is obtained；Judge to whether there is the identity information in background data base；If there are the identity information in background data base, the commodity corresponding with the identity information and favorable rating pre-saved are obtained, the facial expression information when favorable rating browses commodity by acquiring user in advance obtains；Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the commercial product recommending page of the shopping website or the APP that does shopping.The invention also discloses a kind of servers and a kind of computer readable storage medium.The present invention can solve existing commodity personalized recommendation accuracy it is not high the technical issues of.
Description
Technical field
The present invention relates to Internet technical field more particularly to Method of Commodity Recommendation, server and computer-readable storages
Medium.
Background technology
With the continuous development of e-commerce, more and more users like shopping on the web, and user is done shopping by accessing
Website or shopping APP, just can easily select oneself required commodity.
At present, all kinds of shopping websites and shopping APP have the function of personalized recommendation commodity, i.e., are purchased by obtaining user
The data of browsing are bought or clicked to count the degree of commodity welcome, some similar commodity to user-customized recommended are come with this.This
There are following defects for the kind way of recommendation：When user does not buy commodity economic cause or due to not liking, commending system
The welcome degree of commodity can only be counted according to the data that user browses, however user browses certain commodity and do not represent user's happiness
The joyous commodity, the data at this moment browsed simply by user obviously cannot embody user's to count the welcome degree of commodity
True hobby is not high so as to cause the accuracy of personalized recommendation.
Invention content
It is a primary object of the present invention to propose a kind of Method of Commodity Recommendation, server and computer readable storage medium,
Aim to solve the problem that the technical issues of accuracy of existing commodity personalized recommendation is not high.
To achieve the above object, the present invention provides a kind of Method of Commodity Recommendation, and the Method of Commodity Recommendation includes following step
Suddenly：
When detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping website or purchase
The identity information of the user of object APP；
Judge to whether there is the identity information in background data base；
If there are the identity informations in background data base, the quotient corresponding with the identity information pre-saved is obtained
Product and favorable rating, the facial expression information when favorable rating browses commodity by advance acquiring user obtain；
Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the purchase
In the commercial product recommending page of object website or the APP that does shopping.
Optionally, described when detecting default shopping website or shopping APP is opened, acquisition is currently browsing the purchase
Before the step of identity information of the user of object website or the APP that does shopping, further include：
When detect default shopping website or the APP that does shopping in a certain commodity browsed when, obtain and browse the commodity
The identity information of user, and client camera is called to acquire facial expression information when user browses the commodity；
Favorable rating of the user to the commodity is determined according to the facial expression information；
It will be preserved after the identity information association of the user of the determining favorable rating, the commodity and the browsing commodity
Into background data base.
Optionally, it is described when detect default shopping website or do shopping APP in a certain commodity browsed when, obtain browsing
The identity information of the user of the commodity, and facial expression during client camera acquisition user's browsing commodity is called to believe
Before the step of breath, further include：
Setting instruction is received, facial expression information is set for corresponding shopping website or shopping APP according to the setting instruction
Acquire permission.
Optionally, the step of identity information of the user for obtaining the browsing commodity includes：
Judge whether the commodity are browsed under user's login status；
If so, the login account or login name of user is obtained, using the login account or login name as described in browsing
The identity information of the user of commodity；
If it is not, the facial image of the user of the client camera acquisition browsing commodity is then called, by the face figure
As the identity information as the user for browsing the commodity.
Optionally, described the step of determining favorable rating of the user to the commodity according to the facial expression information, wraps
It includes：
User emotion is identified according to the facial expression information；
User emotion according to identifying determines favorable rating of the user to the commodity.
Optionally, the step of user emotion that the basis identifies determines favorable rating of the user to the commodity
Including：
When the user emotion identified is happy or surprised, it is height to the favorable rating of the commodity to determine user；
When the user emotion identified is gentle, in determining that user is to the favorable rating of the commodity；
When the user emotion identified is disappointed or detest, it is low to the favorable rating of the commodity to determine user.
Optionally, described the step of obtaining target Recommendations according to the commodity and favorable rating, includes：
Acquisition favorable rating be high commodity, using the favorable rating for high commodity as target Recommendations；
Alternatively, the similar clause that the favorable rating is high commodity is obtained according to preset rules, by the similar clause
As target Recommendations.
Optionally, it after the step of whether there is the identity information in the judgement background data base, further includes：
If there is no the identity informations in background data base, the identity information is preserved to the background data base
In.
In addition, to achieve the above object, the present invention also provides a kind of server, the server includes：Memory, processing
Device and the commercial product recommending program that can be run on the memory and on the processor is stored in, the commercial product recommending program quilt
The step of processor realizes Method of Commodity Recommendation as described above when performing.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Commercial product recommending program is stored on storage medium, the commercial product recommending program realizes commodity as described above when being executed by processor
The step of recommendation method.
For the present invention when detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping network
Stand or do shopping APP user identity information；Judge to whether there is the identity information in background data base；If background data base
In there are the identity information, then obtain the commodity corresponding with the identity information and favorable rating pre-saved, the happiness
Facial expression information when love degree browses commodity by advance acquiring user obtains；It is obtained according to the commodity and favorable rating
Target Recommendations are taken, the target Recommendations are included in the commercial product recommending page of the shopping website or the APP that does shopping.
The facial expression information when present invention browses commodity by acquiring user in advance, so as to know user to the true of browsing commodity
Real favorable rating carries out subsequent article recommendation according to the true favorable rating of user, can undoubtedly improve the essence of personalized recommendation
Exactness, so as to the present invention solve existing commodity personalized recommendation accuracy it is not high the technical issues of.
Description of the drawings
Fig. 1 is the server architecture schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of Method of Commodity Recommendation first embodiment of the present invention；
Fig. 3 is the display interface schematic diagram of the commercial product recommending page in the embodiment of the present invention；
Fig. 4 is the flow diagram of Method of Commodity Recommendation second embodiment of the present invention；
Fig. 5 is the refinement step schematic diagram that the identity information step for the user for browsing the commodity is obtained in Fig. 4；
Fig. 6 is the flow diagram of Method of Commodity Recommendation 3rd embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are：When detecting default shopping website or shopping APP is opened, obtain
The identity information of the current user for browsing the shopping website or the APP that does shopping；Judge to whether there is institute in background data base
State identity information；To pre-save corresponding with the identity information if there are the identity informations, acquisition in background data base
Commodity and favorable rating, the facial expression information when favorable rating browses commodity by advance acquiring user obtains；
Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the shopping website or
In the commercial product recommending page of shopping APP.
At present, all kinds of shopping websites and shopping APP have the function of personalized recommendation commodity, i.e., are purchased by obtaining user
The data of browsing are bought or clicked to count the degree of commodity welcome, some similar commodity to user-customized recommended are come with this.This
There are following defects for the kind way of recommendation：When user does not buy commodity economic cause or due to not liking, commending system
The welcome degree of commodity can only be counted according to the data that user browses, however user browses certain commodity and do not represent user's happiness
The joyous commodity, the data at this moment browsed simply by user obviously cannot embody user's to count the welcome degree of commodity
True hobby is not high so as to cause the accuracy of personalized recommendation.
The facial expression information when present invention browses commodity by acquiring user in advance, so as to know user to browsing
The true favorable rating of commodity carries out subsequent article recommendation according to the true favorable rating of user, can undoubtedly improve personalization
The accuracy of recommendation, so as to the present invention solve existing commodity personalized recommendation accuracy it is not high the technical issues of.
The present invention provides a kind of Method of Commodity Recommendation.
As shown in Figure 1, the server architecture schematic diagram for the hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to.
Server of the embodiment of the present invention is shopping website or the corresponding background servers of shopping APP, is pushed away to provide commodity
Recommend function.
As shown in Figure 1, the server can include：Processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is used to implement the connection communication between these components.
User interface 1003 can include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 can optionally connect including the wired of standard
Mouth, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory or the memory of stabilization
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
It will be understood by those skilled in the art that the server architecture shown in Fig. 1 does not form the restriction to server, it can
To include either combining certain components or different components arrangement than illustrating more or fewer components.
As shown in Figure 1, it can lead to as in a kind of memory 1005 of computer storage media including operating system, network
Believe module, Subscriber Interface Module SIM and commercial product recommending program.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server
Data communicate；User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication；And processor
1001 can be used for calling the commercial product recommending program stored in memory 1005, and perform following operate：
When detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping website or purchase
The identity information of the user of object APP；
Judge to whether there is the identity information in background data base；
If there are the identity informations in background data base, the quotient corresponding with the identity information pre-saved is obtained
Product and favorable rating, the facial expression information when favorable rating browses commodity by advance acquiring user obtain；
Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the purchase
In the commercial product recommending page of object website or the APP that does shopping.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
When detect default shopping website or the APP that does shopping in a certain commodity browsed when, obtain and browse the commodity
The identity information of user, and client camera is called to acquire facial expression information when user browses the commodity；
Favorable rating of the user to the commodity is determined according to the facial expression information；
It will be preserved after the identity information association of the user of the determining favorable rating, the commodity and the browsing commodity
Into background data base.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
Setting instruction is received, facial expression information is set for corresponding shopping website or shopping APP according to the setting instruction
Acquire permission.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
Judge whether the commodity are browsed under user's login status；
If so, the login account or login name of user is obtained, using the login account or login name as described in browsing
The identity information of the user of commodity；
If it is not, the facial image of the user of the client camera acquisition browsing commodity is then called, by the face figure
As the identity information as the user for browsing the commodity.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
User emotion is identified according to the facial expression information；
User emotion according to identifying determines favorable rating of the user to the commodity.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
When the user emotion identified is happy or surprised, it is height to the favorable rating of the commodity to determine user；
When the user emotion identified is gentle, in determining that user is to the favorable rating of the commodity；
When the user emotion identified is disappointed or detest, it is low to the favorable rating of the commodity to determine user.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
Acquisition favorable rating be high commodity, using the favorable rating for high commodity as target Recommendations；
Alternatively, the similar clause that the favorable rating is high commodity is obtained according to preset rules, by the similar clause
As target Recommendations.
Further, processor 1001 can call the commercial product recommending program stored in memory 1005, also perform following
Operation：
If there is no the identity informations in background data base, the identity information is preserved to the background data base
In.
The specific embodiment of commercial product recommending server of the present invention intercepts each specific implementation of notification method with following pseudo-base stations
Example is essentially identical, and therefore not to repeat here.
Based on above-mentioned hardware configuration, Method of Commodity Recommendation embodiment of the present invention is proposed.
With reference to Fig. 2, flow diagrams of the Fig. 2 for Method of Commodity Recommendation first embodiment of the present invention, the commercial product recommending side
Method includes：
Step S10, when detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping
The identity information of the user of website or the APP that does shopping；
The present embodiment Method of Commodity Recommendation can be realized by the background server of shopping website or the APP that does shopping.First, when
When detecting preset shopping website or shopping APP openings, server, which obtains, is currently browsing the shopping website or shopping APP
User identity information, wherein, identity information can be user login account or login name, or the face of user
Image, or other are capable of the information of unique mark user identity.
Specifically, obtaining the mode of the identity information for the user for currently browsing shopping website or the APP that does shopping can wrap
It includes：Whether detecting user has currently logged in the shopping website or shopping APP；The shopping website has been logged in when detecting user
Or during shopping APP, since the login account or login name of shopping website or shopping APP have the characteristics that repeat, thus can
Using directly acquire user login account or login name as user identity information；It only opens but does not step on when detecting user
When recording the shopping website or shopping APP, then the facial image of client camera acquisition user can be called as user's
Identity information, wherein, client can be PC, notebook, smart mobile phone, tablet computer etc. for user browse shopping website or
The terminal device of shopping APP, and client includes a camera, is called for background server.
Step S20 judges to whether there is the identity information in background data base；
In the step, server carries out the identity information got and the identity information stored in background data base
Match, to judge in background data base with the presence or absence of the identity information got.Specifically, when the identity information got is to log in
When account or login name, then matched with the login account or login name stored in background data base, when in background data base
During in the presence of the login account or login name identical with the login account or login name got, then judge exist in background data base
The identity information；When the identity information got is facial image, then with the facial image that is stored in background data base into
Row matching, when there is the facial image identical with the facial image got in background data base, then judges background data base
In there are the identity information, wherein, match facial image when can refer to facial image matching algorithm of the prior art, herein
It does not repeat.
If there are the identity informations in background data base, step S30 is performed, is obtained pre-saving with the identity
The corresponding commodity of information and favorable rating, the facial expression information when favorable rating browses commodity by acquiring user in advance
And it obtains；
If there is the identity information of the current user for browsing the shopping website or the APP that does shopping in background data base,
The commodity corresponding with the identity information and favorable rating that then server acquisition pre-saves, wherein, favorable rating is by adopting
Obtained from facial expression information when collecting user's past browsing commodity, which represents user emotion, packet
It includes but is not limited to the degree of frowning of user, the corners of the mouth raises up degree, opening and closing degree of mouth etc..
Further, if there is no the current users for browsing the shopping website or the APP that does shopping in background data base
Identity information, then the identity information is preserved into the background data base.
If there is no the identity letters of the current user for browsing the shopping website or the APP that does shopping in background data base
Breath, illustrates that active user is not yet logged background data base, and server preserves the identity information of active user to backstage at this time
In database, later, server can collect the commodity and favorable rating of user browsing corresponding with the user information, then
Three is associated preservation, in this way, when the user accesses the shopping website or shopping APP again, server is i.e. recognizable
Go out the user, and it is user recommendation dependent merchandise to pass through the commodity of the user past browsing of preservation and favorable rating.
Step S40 obtains target Recommendations according to the commodity and favorable rating, the target Recommendations is shown
In the commercial product recommending page of the shopping website or the APP that does shopping.
When the identity letter for judging to have the current user for browsing the shopping website or the APP that does shopping in background data base
Breath, and after getting the commodity corresponding with the identity information and favorable rating pre-saved, server is further according to the quotient
Product and favorable rating obtain target Recommendations.
Specifically, can be according to the step of commodity and favorable rating acquisition target Recommendations：First according to happiness
Commodity are ranked up by love degree, then using the higher commodity of favorable rating as target Recommendations, alternatively, obtaining with liking
The similar commodity of the higher commodity of degree are as target Recommendations.For example, when the commodity of user A past browsings pre-saved
For commodity a, commodity b and commodity c, and corresponding favorable rating be respectively like, generally, it is disagreeable when, can be by commodity a or and quotient
Product a belongs to same type of commodity as target Recommendations, can also belong to by commodity a, commodity b or with commodity a, commodity b
Same type of commodity can flexibly be set as target Recommendations, specific recommendation rules.
After target Recommendations are got, target Recommendations are included pushing away in the commodity of shopping website or the APP that does shopping
Recommend in the page, when it is implemented, can according to the priority display target Recommendations of favorable rating, such as by favorable rating compared with
High target Recommendations are shown in the forward position of recommendation list, and the relatively low target Recommendations of favorable rating are included
Recommendation list rearward position etc., specific display order can flexibly be set, and with reference to Fig. 3, Fig. 3 is commodity in the embodiment of the present invention
Recommend the display interface schematic diagram of the page, 1~n of several target Recommendations is shown in the commercial product recommending page, target recommends quotient
Product can be shown in the form of picture adds title, when user clicks arbitrary commodity, you can enter corresponding commodity details
Displayed page.
For the present invention when detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping network
Stand or do shopping APP user identity information；Judge to whether there is the identity information in background data base；If background data base
In there are the identity information, then obtain the commodity corresponding with the identity information and favorable rating pre-saved, the happiness
Facial expression information when love degree browses commodity by advance acquiring user obtains；It is obtained according to the commodity and favorable rating
Target Recommendations are taken, the target Recommendations are included in the commercial product recommending page of the shopping website or the APP that does shopping.
The facial expression information when present invention browses commodity by acquiring user in advance, so as to know user to the true of browsing commodity
Real favorable rating carries out subsequent article recommendation according to the true favorable rating of user, can undoubtedly improve the essence of personalized recommendation
Exactness, so as to the present invention solve existing commodity personalized recommendation accuracy it is not high the technical issues of.
Further, with reference to Fig. 4, Fig. 4 is the flow diagram of Method of Commodity Recommendation second embodiment of the present invention.Based on upper
Embodiment shown in Fig. 2 is stated, before step S10, can also be included：
Step S50, when detect default shopping website or do shopping APP in a certain commodity browsed when, obtain browsing institute
The identity information of the user of commodity is stated, and facial expression during client camera acquisition user's browsing commodity is called to believe
Breath；
Step S60 determines favorable rating of the user to the commodity according to the facial expression information；
Step S70 closes the identity information of the user of the determining favorable rating, the commodity and the browsing commodity
It is preserved after connection into background data base.
In the present embodiment, to ensure that commercial product recommending is smoothed out, server need to collect the letter that user browses commodity in advance
Breath, the reference data recommended as subsequent article.Specific collection mode is as follows：
Firstly, since user can generally open the commodity page to browse the details of a certain commodity, therefore work as server
Detect default shopping website or the APP that does shopping in a certain commodity page when being opened, it is possible to determine that the commodity are by user
Browsing, at this point, server obtains the identity information for the user for browsing the commodity.It is obtained described in browsing for step with reference to Fig. 5, Fig. 5
The step of refinement step schematic diagram of the identity information of the user of commodity, the identity information for the user for obtaining the browsing commodity, can
To include：
Step S51, judges whether the commodity are browsed under user's login status；
If so, performing step S52, the login account or login name of user are obtained, by the login account or login name
Identity information as the user for browsing the commodity；
If it is not, then performing step S53, the acquisition of client camera is called to browse the facial image of the user of the commodity,
Using the facial image as the identity information for the user for browsing the commodity.
Whether server detecting user has currently logged in the shopping website or shopping APP, if so, judging the commodity
It is to be browsed under user's login status, server obtains the login account or login name of user at this time, and by the login account
Number or login name as browsing current commodity user identity information；If it is not, then server calls it to take the photograph to client transmission
As the request of head, after the permission information for receiving client return, client camera acquisition browsing current commodity is called
The facial image of user, and using the facial image as the identity information of the user of browsing current commodity.In this way, no matter user
The identity information of active user can be collected by whether logging in shopping website or shopping APP, server.
While the identity information for obtaining the user for browsing the commodity, server calls client camera is to acquire
User browses facial expression information during current commodity, then can determine user to it according to collected facial expression information
The favorable rating of the commodity of browsing, such as when it is to frown to recognize facial expression, it is possible to determine that user does not like current browsing
Commodity, when recognize facial expression for smile when, it is possible to determine that user likes the commodity currently browsed.
Later, server will preserve after the identity information association of the user of determining favorable rating, commodity and browsing commodity
Into background data base, the reference data as subsequent article recommendation.
Further, before above-mentioned steps S50, step can also be included：Setting instruction is received, is referred to according to the setting
It enables and facial expression information is set to acquire permission for corresponding shopping website or shopping APP.
In the present embodiment, it is contemplated that certain user, which may not want that, reveals the facial expression information of oneself, and user can thus
Facial expression information is set to acquire permission for corresponding shopping website or shopping APP in advance to enter corresponding setting interface, when and
Only when the facial expression information of user setting acquisition permission is allows, corresponding shopping website or shopping APP could call camera shooting
Head acquisition facial expression information, and and then perform the present embodiment above-mentioned commercial product recommending process.It so can be according to the hidden of oneself
Private needs to choose whether progress commercial product recommending, improves user experience.
Further, with reference to Fig. 6, Fig. 6 is the flow diagram of Method of Commodity Recommendation 3rd embodiment of the present invention.Based on upper
Embodiment shown in Fig. 4 is stated, step S60 can include：
Step S61 identifies user emotion according to the facial expression information；
Step S62 determines favorable rating of the user to the commodity according to the user emotion identified.
In the present embodiment, server, can be first according to the face table after the facial expression information of user is collected
Feelings information identifies user emotion, then determines favorable rating of the user to the commodity according to the user emotion identified.Wherein,
The type of user emotion can flexibly be set in advance, and the correspondence of user emotion and user between the favorable rating of commodity also may be used
Flexibly setting；Specific Emotion identification algorithm can refer to the prior art, not repeat herein.
Further, above-mentioned steps S62 can include：When the user emotion identified is happy or surprised, determine to use
Family is height to the favorable rating of the commodity；When the user emotion identified is gentle, happiness of the user to the commodity is determined
During love degree is；When the user emotion identified is disappointed or detest, it is low to the favorable rating of the commodity to determine user.
The step of obtaining target Recommendations according to the commodity and favorable rating at this time can include：Obtain favorable rating
It is high commodity as target Recommendations using the favorable rating for high commodity；Alternatively, described in obtaining according to preset rules
Favorable rating is the similar clause of high commodity, using the similar clause as target Recommendations.
In the present embodiment, user emotion can be divided into positive mood (happy, surprised), neutral mood (gentle) is born
Face mood (disappointed or detest), it is respectively height to the favorable rating of commodity to correspond to user, in, it is low.Later, when the use identified
When family mood is happy or surprised, it is height to the favorable rating of commodity to determine user；When the user emotion identified is gentle,
In determining that user is to the favorable rating of commodity；When the user emotion identified is disappointed or detest, determine user to commodity
Favorable rating to be low, so can accurately reflect favorable rating of the user to commodity.
When it is follow-up determine target Recommendations when, can using favorable rating for high commodity as target Recommendations；Or
Person obtains the similar clause that the favorable rating is high commodity according to preset rules, the similar clause is pushed away as target
Commodity are recommended, wherein, the rule for obtaining similar clause can be to obtain commodity or the acquisition of type identical (such as electric type, clothing)
Identical commodity of title etc., specific acquisition modes can refer to existing similar clause proposed algorithm, do not repeat herein.Due to mesh
It is to be obtained according to the favorable rating of user, therefore the hobby that can more be close to the users to mark Recommendations, improves commodity individual character
Change the accuracy recommended.
The present invention also provides a kind of computer readable storage mediums.
Commercial product recommending program is stored on computer readable storage medium of the present invention, the commercial product recommending program is by processor
Following steps are realized during execution：
When detecting default shopping website or shopping APP is opened, acquisition is currently browsing the shopping website or purchase
The identity information of the user of object APP；
Judge to whether there is the identity information in background data base；
If there are the identity informations in background data base, the quotient corresponding with the identity information pre-saved is obtained
Product and favorable rating, the facial expression information when favorable rating browses commodity by advance acquiring user obtain；
Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the purchase
In the commercial product recommending page of object website or the APP that does shopping.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
When detect default shopping website or the APP that does shopping in a certain commodity browsed when, obtain and browse the commodity
The identity information of user, and client camera is called to acquire facial expression information when user browses the commodity；
Favorable rating of the user to the commodity is determined according to the facial expression information；
It will be preserved after the identity information association of the user of the determining favorable rating, the commodity and the browsing commodity
Into background data base.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
Setting instruction is received, facial expression information is set for corresponding shopping website or shopping APP according to the setting instruction
Acquire permission.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
Judge whether the commodity are browsed under user's login status；
If so, the login account or login name of user is obtained, using the login account or login name as described in browsing
The identity information of the user of commodity；
If it is not, the facial image of the user of the client camera acquisition browsing commodity is then called, by the face figure
As the identity information as the user for browsing the commodity.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
User emotion is identified according to the facial expression information；
User emotion according to identifying determines favorable rating of the user to the commodity.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
When the user emotion identified is happy or surprised, it is height to the favorable rating of the commodity to determine user；
When the user emotion identified is gentle, in determining that user is to the favorable rating of the commodity；
When the user emotion identified is disappointed or detest, it is low to the favorable rating of the commodity to determine user.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
Acquisition favorable rating be high commodity, using the favorable rating for high commodity as target Recommendations；
Alternatively, the similar clause that the favorable rating is high commodity is obtained according to preset rules, by the similar clause
As target Recommendations.
Further, following steps are also realized when the commercial product recommending program is executed by processor：
If there is no the identity informations in background data base, the identity information is preserved to the background data base
In.
Wherein, the commercial product recommending program run on the processor is performed realized method and can refer to the present invention
The each embodiment of Method of Commodity Recommendation, details are not described herein again.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those elements, and
And it further includes other elements that are not explicitly listed or further includes intrinsic for this process, method, article or system institute
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), used including some instructions so that a station terminal server (can be hand
Machine, computer, server, air conditioner or network server etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made directly or indirectly is used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Method of Commodity Recommendation, which is characterized in that the Method of Commodity Recommendation includes the following steps：
When detecting default shopping website or shopping APP is opened, obtain and currently browsing the shopping website or shopping APP
User identity information；
Judge to whether there is the identity information in background data base；
If there are the identity information in background data base, obtain the commodity corresponding with the identity information that pre-save and
Favorable rating, the facial expression information when favorable rating browses commodity by advance acquiring user obtain；
Target Recommendations are obtained according to the commodity and favorable rating, the target Recommendations are included in the shopping network
It stands or does shopping in the commercial product recommending page of APP.
2. Method of Commodity Recommendation as described in claim 1, which is characterized in that described to detect default shopping website or shopping
APP open when, obtain currently browsing the shopping website or do shopping APP user identity information the step of before, also
Including：
When detect default shopping website or the APP that does shopping in a certain commodity browsed when, obtain the user for browsing the commodity
Identity information, and call client camera acquisition user browse the commodity when facial expression information；
Favorable rating of the user to the commodity is determined according to the facial expression information；
It will be preserved after the identity information association of the user of the determining favorable rating, the commodity and the browsing commodity to rear
In platform database.
3. Method of Commodity Recommendation as claimed in claim 2, which is characterized in that described to detect default shopping website or shopping
When a certain commodity in APP are browsed, the identity information for the user for browsing the commodity is obtained, and client camera is called to adopt
Collect user browse the commodity when facial expression information the step of before, further include：
Setting instruction is received, facial expression information is set to acquire for corresponding shopping website or shopping APP according to the setting instruction
Permission.
4. Method of Commodity Recommendation as claimed in claim 2, which is characterized in that the body for obtaining the user for browsing the commodity
The step of part information, includes：
Judge whether the commodity are browsed under user's login status；
If so, the login account or login name of user is obtained, using the login account or login name as the browsing commodity
User identity information；
If it is not, then calling the facial image of the user of the client camera acquisition browsing commodity, the facial image is made
Identity information for the user for browsing the commodity.
5. Method of Commodity Recommendation as claimed in claim 2, which is characterized in that described to determine to use according to the facial expression information
Family includes the step of favorable ratings of the commodity：
User emotion is identified according to the facial expression information；
User emotion according to identifying determines favorable rating of the user to the commodity.
6. Method of Commodity Recommendation as claimed in claim 5, which is characterized in that the user emotion that the basis identifies is true
The step of determining favorable rating of the user to the commodity includes：
When the user emotion identified is happy or surprised, it is height to the favorable rating of the commodity to determine user；
When the user emotion identified is gentle, in determining that user is to the favorable rating of the commodity；
When the user emotion identified is disappointed or detest, it is low to the favorable rating of the commodity to determine user.
7. Method of Commodity Recommendation as claimed in claim 6, which is characterized in that described to be obtained according to the commodity and favorable rating
The step of target Recommendations, includes：
Acquisition favorable rating be high commodity, using the favorable rating for high commodity as target Recommendations；
Alternatively, obtain the similar clause that the favorable rating is high commodity according to preset rules, using the similar clause as
Target Recommendations.
8. the Method of Commodity Recommendation as described in any one of claim 1 to 7, which is characterized in that the judgement background data base
In whether there is the identity information the step of after, further include：
If there is no the identity informations in background data base, the identity information is preserved into the background data base.
9. a kind of server, which is characterized in that the server includes：It memory, processor and is stored on the memory
And the commercial product recommending program that can be run on the processor, it is realized such as when the commercial product recommending program is performed by the processor
The step of Method of Commodity Recommendation described in any item of the claim 1 to 8.
10. a kind of computer readable storage medium, which is characterized in that be stored with commodity on the computer readable storage medium and push away
Program is recommended, such as commercial product recommending described in any item of the claim 1 to 8 is realized when the commercial product recommending program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711442801.3A CN108182624A (en) | 2017-12-26 | 2017-12-26 | Method of Commodity Recommendation, server and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711442801.3A CN108182624A (en) | 2017-12-26 | 2017-12-26 | Method of Commodity Recommendation, server and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108182624A true CN108182624A (en) | 2018-06-19 |
Family
ID=62547572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711442801.3A Pending CN108182624A (en) | 2017-12-26 | 2017-12-26 | Method of Commodity Recommendation, server and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182624A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583970A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Advertisement placement method, device, computer equipment and storage medium |
| CN109685611A (en) * | 2018-12-15 | 2019-04-26 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, apparatus, computer equipment and storage medium |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
| CN109829784A (en) * | 2019-01-17 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
| CN109858960A (en) * | 2019-01-21 | 2019-06-07 | 平安科技（深圳）有限公司 | Commodity method for pushing, device, subscriber information management server and storage medium |
| CN110648187A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Commodity information display method and preference information display method |
| CN110766498A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for recommending commodities |
| CN110781399A (en) * | 2019-10-31 | 2020-02-11 | 深圳市云积分科技有限公司 | Cross-platform information pushing method and device |
| WO2020125217A1 (en) * | 2018-12-18 | 2020-06-25 | 深圳云天励飞技术有限公司 | Expression recognition method and apparatus and recommendation method and apparatus |
| CN111598671A (en) * | 2020-07-20 | 2020-08-28 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN111612576A (en) * | 2020-05-09 | 2020-09-01 | 向培红 | Commodity recommendation method and device and electronic equipment |
| CN111861660A (en) * | 2020-07-16 | 2020-10-30 | 深圳市爱乐墨科技有限公司 | Blessing information matching method and device and storage medium |
| CN111986005A (en) * | 2020-08-31 | 2020-11-24 | 上海博泰悦臻电子设备制造有限公司 | Activity recommendation method and related equipment |
| CN112348640A (en) * | 2020-11-12 | 2021-02-09 | 北京科技大学 | Online shopping system and method based on facial emotion state analysis |
| CN112507228A (en) * | 2020-12-14 | 2021-03-16 | 北京达佳互联信息技术有限公司 | Content recommendation method and content recommendation device |
| CN112581230A (en) * | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
| CN112767069A (en) * | 2020-12-31 | 2021-05-07 | 青岛海尔科技有限公司 | Commodity recommendation method and device, storage medium and electronic device |
| CN116017000A (en) * | 2022-12-27 | 2023-04-25 | 深圳创维－Rgb电子有限公司 | Shopping recommendation method and device based on intelligent television, intelligent television and medium |
| CN116091153A (en) * | 2022-11-23 | 2023-05-09 | 北京学两招科技有限公司 | Data management method, system and storage medium of e-commerce platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1898958A (en) * | 2003-12-22 | 2007-01-17 | 皇家飞利浦电子股份有限公司 | Content- processing system, method, and computer program product for monitoring the viewer's mood |
| CN103098079A (en) * | 2011-04-11 | 2013-05-08 | 英特尔公司 | Personalized program selection system and method |
| KR20130119246A (en) * | 2012-04-23 | 2013-10-31 | 한국전자통신연구원 | Apparatus and method for recommending contents based sensibility |
-
2017
- 2017-12-26 CN CN201711442801.3A patent/CN108182624A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1898958A (en) * | 2003-12-22 | 2007-01-17 | 皇家飞利浦电子股份有限公司 | Content- processing system, method, and computer program product for monitoring the viewer's mood |
| CN103098079A (en) * | 2011-04-11 | 2013-05-08 | 英特尔公司 | Personalized program selection system and method |
| KR20130119246A (en) * | 2012-04-23 | 2013-10-31 | 한국전자통신연구원 | Apparatus and method for recommending contents based sensibility |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648187A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Commodity information display method and preference information display method |
| CN110766498A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for recommending commodities |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
| CN109583970A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Advertisement placement method, device, computer equipment and storage medium |
| CN109685611A (en) * | 2018-12-15 | 2019-04-26 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, apparatus, computer equipment and storage medium |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
| WO2020125217A1 (en) * | 2018-12-18 | 2020-06-25 | 深圳云天励飞技术有限公司 | Expression recognition method and apparatus and recommendation method and apparatus |
| CN109829784A (en) * | 2019-01-17 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
| CN109858960A (en) * | 2019-01-21 | 2019-06-07 | 平安科技（深圳）有限公司 | Commodity method for pushing, device, subscriber information management server and storage medium |
| CN110781399A (en) * | 2019-10-31 | 2020-02-11 | 深圳市云积分科技有限公司 | Cross-platform information pushing method and device |
| CN111612576A (en) * | 2020-05-09 | 2020-09-01 | 向培红 | Commodity recommendation method and device and electronic equipment |
| CN111861660A (en) * | 2020-07-16 | 2020-10-30 | 深圳市爱乐墨科技有限公司 | Blessing information matching method and device and storage medium |
| CN111598671A (en) * | 2020-07-20 | 2020-08-28 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN111598671B (en) * | 2020-07-20 | 2020-10-30 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN111986005A (en) * | 2020-08-31 | 2020-11-24 | 上海博泰悦臻电子设备制造有限公司 | Activity recommendation method and related equipment |
| CN112348640A (en) * | 2020-11-12 | 2021-02-09 | 北京科技大学 | Online shopping system and method based on facial emotion state analysis |
| CN112348640B (en) * | 2020-11-12 | 2021-08-13 | 北京科技大学 | Online shopping system and method based on facial emotion state analysis |
| CN112507228A (en) * | 2020-12-14 | 2021-03-16 | 北京达佳互联信息技术有限公司 | Content recommendation method and content recommendation device |
| CN112581230A (en) * | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
| CN112767069A (en) * | 2020-12-31 | 2021-05-07 | 青岛海尔科技有限公司 | Commodity recommendation method and device, storage medium and electronic device |
| CN116091153A (en) * | 2022-11-23 | 2023-05-09 | 北京学两招科技有限公司 | Data management method, system and storage medium of e-commerce platform |
| CN116017000A (en) * | 2022-12-27 | 2023-04-25 | 深圳创维－Rgb电子有限公司 | Shopping recommendation method and device based on intelligent television, intelligent television and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182624A (en) | Method of Commodity Recommendation, server and computer readable storage medium | |
| US11272032B2 (en) | Intelligent display of information in a user interface | |
| US8180858B2 (en) | Method and system for presenting data over a network based on network user choices and collecting real-time data related to said choices | |
| US11200274B2 (en) | Method of e-commerce | |
| CN108960975A (en) | Personalized Precision Marketing Method, server and storage medium based on user's portrait | |
| US20170364991A1 (en) | Merchandise recommendation device, merchandise recommendation method, and program | |
| US20230014418A1 (en) | Recommending contents using a base profile | |
| US20150046496A1 (en) | Method and system of generating an implicit social graph from bioresponse data | |
| US20100100566A1 (en) | Methods and Systems for Identifying the Fantasies of Users Based on Image Tagging | |
| CN106878405B (en) | Method and device for adjusting push items | |
| CN104903929A (en) | Providing content recommendation to users on a site | |
| US8954868B2 (en) | Guided profile editing system | |
| WO2012006109A1 (en) | Method and system for obtaining mobile metrics | |
| US20230091110A1 (en) | Joint embedding content neural networks | |
| CN107562939A (en) | Vertical domain news recommendation method and device and readable storage medium | |
| US10176535B2 (en) | Method and system for providing social category indicators in a user profile header of an on-line posting | |
| CN108717403B (en) | Processing method and device for processing | |
| WO2020073524A1 (en) | Method and apparatus for recommending a product offline, and electronic device | |
| CN108829773A (en) | Mobile terminal reads recommended method, mobile terminal and computer readable storage medium | |
| US9449025B1 (en) | Determining similarity using human generated data | |
| CN107967637B (en) | Commodity object model recommendation method and device and electronic equipment | |
| US20160260017A1 (en) | Method for adapting user interface and functionalities of mobile applications according to the user expertise | |
| KR100985949B1 (en) | System and method for providing product information service by mobile network system | |
| CN105893624A (en) | Method and system for displaying data | |
| CN108846036A (en) | Mobile terminal reads recommended method, mobile terminal and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |